Top Tweets for #machineLarning
Artificial Intelligence vs Machine Learning vs Deep Learning: Key Differences Explained in 2026
#AI #artificialIntelligence #deepLearning #machineLarning
https://t.co/OgUFMKZXK5
Feature selection
Pearson correlation
#machinelarning

*/ I constantly see people rise in life who are not the smartest, sometimes not even the most diligent……but they are learning machines. */
— Charlie Munger
> BTW 2025 isn’t for the genius.
> It’s for the obsessed learner.
#machinelarning #charliemunger

Tomorrow is a special day, because it's Pi Day 🥧
To celebrate, go to 👉 https://t.co/zJk7fh3dXA tomorrow at 9AM PT for AWS Pi Day to learn more about data, analytics, and see demos from #AmazonSageMaker & #AmazonS3
See you there!
#AWS #ai #machinelarning
A Reminder of an old yet Gold Modeling Trick(Choosing the model) in #MachineLarning that never dies 🧑💻🤖🚀:
- Linear regression (l1/l2 as norms and elasticnet as regularization) as a starter.
- LightGBM for pretty much everything as it’s fast and accurate.
- CatBoost if you have many categorical features.
- Random Forest if your OOS variance is too high from LightGBM.
- XGBoost when you’re just curious.
- Ensemble multiple models and average the preds using postprocessing techniques like weighted average, median, etc, as well as run feature neutralisation.
Also, Random Forest is a Swiss knife of data science, albeit less powerful (but almost as powerful for most tasks unless one is going for that extra 0.001 on Kaggle) than boosted trees (CatBoost/LightGBM/XGBoost).
It is almost as powerful whilst much less fragile in terms of overfitting and less sensitive to hyperparameters. One can use Random Forest out of the box to get a good benchmark; less known is that XGBoost contains a faster implementation of Random Forest.
Note: Out-of-Specification (OOS) variance is when a sample's test results do not meet the established acceptance criteria.
Follow @trawasthi_ai for more contents that make ML, Deep Learning, Maths, etc. simple to understand.
#MachineLearning #DeepLearning #Maths #GenAI #100DaysOfCode
This year's #NobelPrize announcement took the world by surprise, leaving many to wonder if #machinelarning and #AI can truly be considered "physics". We share one writer's perspective on both the history of AI and how it relates to physics: https://t.co/R6e9aegPM1

Automatically fine-tune parameter set-points in real-time & let our #AI Operator provide continuous process diagnosis, catching issues early and ensuring smooth, efficient operations. Stay ahead with intelligent, proactive control!
#PredictiveControl #MachineLarning #SaaS #Haber

A Reminder of an old Modeling Trick(Choosing the model) in #MachineLarning that never dies 🧑💻🤖🚀:
- Linear regression (l1/l2 as norms and elasticnet as regularization) as a starter.
- LightGBM for pretty much everything as it’s fast and accurate.
- CatBoost if you have many categorical features.
- Random Forest if your OOS variance is too high from LightGBM.
- XGBoost when you’re just curious.
- Ensemble multiple models and average the preds using postprocessing techniques like weighted average, median, etc, as well as run feature neutralisation.
Also, Random Forest is a Swiss knife of data science, albeit less powerful (but almost as powerful for most tasks unless one is going for that extra 0.001 on Kaggle) than boosted trees (CatBoost/LightGBM/XGBoost).
It is almost as powerful whilst much less fragile in terms of overfitting and less sensitive to hyperparameters. One can use Random Forest out of the box to get a good benchmark; less known is that XGBoost contains a faster implementation of Random Forest.
Note: Out-of-Specification (OOS) variance is when a sample's test results do not meet the established acceptance criteria.
#MachineLearning #DeepLearning #GenAI #LLM #Grok2images #grokai #100DaysOfCode

Advance your career with us! Apply for a #HorizonEurope #MSCA European #PostdoctoralFellowship with Prof Alessio Benavoli on #HumancentredAI
Submit your expression of interest today! https://t.co/BbucHlXZnM
#MachineLarning #BayesianOptimisation #ReinforcementLearning #AI

"Attending to Topological Spaces: The Cellular Transformer" by @rballeba, @mathildepapillo, @ClaBat9 , @ninamiolane, @tolga_birdal, @carlescasac, @SergioEscalera_ , @HajijMustafa et al.
Paper: https://t.co/FSJ3lQYICS
#machinelarning #topologicaldeeplearning

Interested in the impact of Covid-19 vaccination on mortality risk prediction in nursing home residents?
Our latest study utilizes machine learning techniques in a retrospective cohort analysis to examine this. #COVID19 #machinelarning
https://t.co/yjhcPJZRHS
Cryptocurrency is the new Linux Distro fighting to become the next Windows competitor. 👽
@elonmusk #ArtificialIntelligence #augmentedreality #coding #programming #softwaredevelopment #webdev #python #web3 #kotlin #php #algorithms #machinelarning #artificialintelligence
This is broken on 70% of cars & costs $10 @elonmusk #ArtificialIntelligence #augmentedreality #coding #programming #softwaredevelopment #webdev #python #web3 #kotlin #php #algorithms #machinelarning #artificialintelligence #cybersecurity #mobiledev #gamingpc #GamingLife #art

Most Popular Users

Elon Musk 
@elonmusk
240.5M followers

Barack Obama 
@barackobama
119.3M followers

Donald J. Trump 
@realdonaldtrump
111.7M followers

Cristiano Ronaldo 
@cristiano
110.4M followers

Narendra Modi 
@narendramodi
107M followers

Rihanna 
@rihanna
97.6M followers

NASA 
@nasa
92.1M followers

Justin Bieber 
@justinbieber
90.9M followers

KATY PERRY 
@katyperry
87.5M followers

Taylor Swift 
@taylorswift13
81.4M followers

Lady Gaga 
@ladygaga
72.9M followers

Kim Kardashian 
@kimkardashian
69.7M followers

Virat Kohli 
@imvkohli
69.7M followers

YouTube 
@youtube
68.7M followers

Bill Gates 
@billgates
63.8M followers

The Ellen Show
@theellenshow
62.5M followers

Neymar Jr 
@neymarjr
62.4M followers

CNN 
@cnn
61.9M followers

X 
@x
60.8M followers

Selena Gomez 
@selenagomez
60.6M followers
















